EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Crack Segmentation and Geometric Parameter Calculation of Mandrel Bars Based on an Improved YOLO Framework

Jianzhao Cao, Zhu Sun, Jingguo Ding, Xu Li

Metals · 14.06.2026 · 16 (6) · 657

DOI: 10.3390/met16060657 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Metals, online erschienen am 14.06.2026. Verfasst von Jianzhao Cao und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Science and Technology Program, Key Research Projects of the Education Department of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Surface cracks on mandrel bars affect product quality and production stability in seamless steel pipe manufacturing. Existing vision-based methods mainly rely on bounding-box detection, which is insufficient for precise crack delineation and geometric characterization. This study proposes a lightweight segmentation framework for online mandrel bar crack inspection using grayscale industrial images. Based on YOLO11n-seg, the framework incorporates single-channel input adaptation, lightweight network reconfiguration, and crack-oriented feature enhancement to improve the extraction of weak, thin, and irregular cracks while reducing computational cost. A dedicated industrial dataset and a sample-balancing strategy are introduced to alleviate severe crack–background imbalance. Based on the predicted pixel-level masks, crack area, projected length, maximum width, and average width are calculated for online evaluation. Experimental results show that the proposed method achieves a mask mAP@0.5 of 88.5%, a false negative rate of 1.72%, and real-time inference at 204 FPS with 3.01 GFLOPs. Field deployment further demonstrates the effectiveness of the proposed framework for online crack inspection and geometric parameter calculation of mandrel bars.

Förderung

  • Liaoning Provincial Science and Technology Program
  • Key Research Projects of the Education Department of Liaoning Province

Zitieren

APA

Cao, J., Sun, Z., Ding, J., & Li, X. (2026). Real-Time Crack Segmentation and Geometric Parameter Calculation of Mandrel Bars Based on an Improved YOLO Framework. Metals, 16(6), 657. https://doi.org/10.3390/met16060657

Vancouver

Cao J, Sun Z, Ding J, Li X. Real-Time Crack Segmentation and Geometric Parameter Calculation of Mandrel Bars Based on an Improved YOLO Framework. Metals. 2026;16(6):657. doi:10.3390/met16060657

BibTeX
@article{Cao2026,
  author = {Cao, Jianzhao and Sun, Zhu and Ding, Jingguo and Li, Xu},
  title = {Real-Time Crack Segmentation and Geometric Parameter Calculation of Mandrel Bars Based on an Improved YOLO Framework},
  journal = {Metals},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {657},
  doi = {10.3390/met16060657}
}
Kostenlos starten →